We are delighted today to be announcing the beta release of our pgEdge Agentic AI Toolkit for Postgres. We’ve had the benefit of collaborating on real-world Postgres-based AI applications the past two years with a number of leading customers, and this product announcement is the outgrowth of this learning.

We listened to customers as they refined their AI strategies in response to the rapid evolution of LLMs, Agentic AI and integration technologies such as the Model Context Protocol (MCP), and as we did so a few things stood out to us.

First and foremost, many of the newly available tools and technologies are not suited to the needs of the enterprise, particularly in highly regulated industries or major government agencies. Many of the new AI application builders and code generators – and the database platforms supporting them – do not adequately address enterprise requirements for high availability, data sovereignty, global deployment, security and compliance and the need in some cases to run on-premises or in self-managed cloud accounts. As one CIO in financial services put it to us recently: “We’ve got a couple of dozen AI generated applications end users really want to put into production, but first we’ve got to figure out how to deploy them on our own internal compliant infrastructure.”

Secondly, as compelling as it is to automate workflows with Agentic AI, or to generate new applications with tools like Claude Code, Replit, Cursor or Lovable, the biggest need is to work with existing databases and applications. While newer Postgres-based cloud services work well with Agentic AI and AI app builders for brand new applications, they cannot accommodate existing databases and applications without a costly migration. And such a migration may well be to an environment that doesn’t meet the organization’s strict security and compliance requirements. Enterprise customers need AI tooling – including an MCP Server – that can operate against their existing databases.

Additionally we saw there was no dedicated Postgres vendor offering a fully featured and fully supported MCP Server that works with all your existing Postgres databases. Most of the available Postgres MCP Servers are tied to the vendor’s own products, and in particular their cloud database offering.

And thirdly, developing new AI applications – such as a chatbot running on top of an existing knowledge base – is overly complex with developers having to stitch together too many tools, APIs, Postgres extensions and data pipelines. We saw an opportunity to make it easier to develop AI applications without having to undertake a major exercise in tool sourcing and integration.

We are addressing each of these with the pgEdge Agentic AI Toolkit for Postgres. Together with pgEdge Enterprise Postgres or pgEdge Distributed Postgres it delivers on enterprise requirements such as high availability, data sovereignty and flexible deployment on-premises, in self managed cloud accounts or soon in our pgEdge Cloud managed cloud service.However, it is not tied to just our own Postgres offerings. The pgEdge Agentic AI Toolkit for Postgres, and in particular the included pgEdge Postgres MCP Server, work with any standard version of Postgres, including community Postgres and Amazon RDS. This means you can download the toolkit from pgEdge, quickly configure Claude Code, Replit or Cursor (and others) to use the pgEdge MCP Server (see here), and then in minutes be generating new UIs, applications and workflows running on top of your existing databases. Or alternatively connect the pgEdge MCP Server to Claude Desktop, and use it to make recommendations for scaling and performance improvements. We could be biased, but we think this is a pretty big deal.

Key components of the pgEdge Agentic AI Toolkit include:

The aforementioned pgEdge MCP Server, a highly performant and full featured MCP Server. It provides LLMs and agents with a secure connection to access Postgres databases and obtain detailed information about database structure and schemas, allowing them to reason about the data, schema, and performance metrics held within.

Natural Language Agents for querying data, available via a command line interface (CLI) or a web user interface. These are full-featured MCP clients in Go, with Anthropic prompt caching (for a 90% cost reduction). The web client features a Modern React-based UI, demonstrating AI-powered chat for natural language database interaction.

pgEdge-vectorizer, a Postgres extension that automatically chunks text content and generates vector embeddings using background workers, providing a simple SQL interface for enabling vectorization on any table. Vector embeddings are automatically kept updated as the content changes. pgEdge-vectorizer has no dependencies other than pgvector and a connection to your LLM of choice.

pgEdge RAG Server, a dedicated API Server for performing Retrieval-Augmented Generation (RAG) of text based on content from a PostgreSQL database using pgvector.

pgEdge-docloader, a utility that makes it easy to bring initial material online and make it searchable by agents and can be used in conjunction with the pgEdge RAG Server and pgEdge Vectorizer. No external services or third-party pipelines are required beyond an embedding LLM provider.

VectorChord-bm25, a Postgres extension implementing BM25 ranked search for hybrid semantic and full-text searching. Also included are the pgvector, pg_tokenizer.rs and pg_vectorize extensions.

pgEdge Agentic AI Toolkit for Postgres is fully open source, and available for free to all Postgres users. The pgEdge MCP Server works with Postgres versions from v14 on, other Toolkit components v16 on. pgEdge customers with paid subscriptions for pgEdge Enterprise Postgres or pgEdge Distributed Postgres receive support at no extra cost. For self-hosted and self-managed deployment the product documentation and download can be found here. It will be available within the pgEdge Cloud managed service in Q1 2026.

Today’s announcement is really just the beginning. We look forward to seeing how developers use it to bring Agentic AI and AI generated apps to both new and existing databases while being able to deploy on enterprise grade infrastructure. And we’d love to get your feedback!

P.S. This blog post was entirely written by hand. Any use of emdashes or bullet points is entirely my own doing.

*Got questions or feedback about the pgEdge Postgres MCP server? Hit us up on the *pgEdge Discord or open an issue on GitHub. We’re here to help.